On a probabilistic approach to synthesize control policies from example datasets

DOI10.1016/j.automatica.2021.110121zbMath1482.93587arXiv2005.11191OpenAlexW3027624373MaRDI QIDQ2071969

Giovanni Russo, Davide Gagliardi

Publication date: 31 January 2022

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.11191

Mathematics Subject Classification ID

Synthesis problems (93B50) Stochastic systems in control theory (general) (93E03)

Related Items (1)

Model-based preference quantification

Uses Software

• OpenStreetMap

Cites Work

• Unnamed Item
• Optimal control as a graphical model inference problem
• Axiomatisation of fully probabilistic design
• Towards fully probabilistic control design
• Fully probabilistic control for stochastic nonlinear control systems with input dependent noise
• The role of duality in optimization problems involving entropy functionals with applications to information theory
• Bayesian system identification
• New methods for linear inequalities
• Two applications of a consistency theorem for systems of linear inequalities
• Data informativity for the open-loop identification of MIMO systems in the prediction error framework
• Data-driven control of nonlinear systems: an on-line direct approach
• From model-based control to data-driven control: survey, classification and perspective
• Fully probabilistic control design
• On infinite systems of linear inequalities
• Online Markov Decision Processes With Kullback–Leibler Control Cost
• Efficient computation of optimal actions
• Linear Inequalities and Related Systems. (AM-38)
• Kullback-leibler approximation of spectral density functions
• Solving Systems of Linear Equations and Inequalities
• On the Existence of a Solution to a Spectral Estimation Problem <italic>à la</italic> Byrnes–Georgiou–Lindquist
• Learning Model Predictive Control for Iterative Tasks. A Data-Driven Control Framework
• Controller Synthesis Free of Analytical Models: Three Term Controllers
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness
• Learning Policies for Markov Decision Processes From Data
• Entropy, optimization and counting
• On the Georgiou–Lindquist Approach to Constrained Kullback–Leibler Approximation of Spectral Densities
• Elements of Information Theory
• Optimal Experimental Designs
• Duality for optimization problems with entropy-like objective functions
• On Information and Sufficiency
• Data Informativity: A New Perspective on Data-Driven Analysis and Control

This page was built for publication: On a probabilistic approach to synthesize control policies from example datasets